© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50447
    Prev
    Next
    INDEX
    Explanations

    time with am/pm

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to numeric tokens—especially digits used in times, dates, and schedule information.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Evening
    -1.20
     evening
    -1.11
     evenings
    -1.08
     sunsets
    -1.01
    evening
    -1.01
     Evening
    -0.91
    dinner
    -0.91
    Afternoon
    -0.91
    Tonight
    -0.90
    Dinner
    -0.87
    POSITIVE LOGITS
     morning
    1.71
     AM
    1.59
    am
    1.54
     am
    1.52
    AM
    1.31
    上午
    1.14
     Morning
    1.13
    午前
    1.12
     Am
    1.09
     MORNING
    1.09
    Activations Density 0.021%

    No Known Activations